AI Paper Atlas

Research map / Image generation / Image restoration

One Network to Solve Them All -- Solving Linear Inverse Problems Using Deep Projection Models

J. H. Rick Chang, Chun-Liang Li, Barnabas Poczos, B. V. K. Vijaya Kumar, Aswin C. Sankaranarayanan

ICCV 2017 · Image generation › Image restoration · approach: Priors for restoration networks · 350 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use smooth ELU activations and truncated weights in the classifiers instead of non-smooth leaky ReLU (ablation)deep projection model within ADMM · Scattered inpainting on ImageNetRMSE of x - z (ADMM convergence)Improved
replace the wavelet l1 prior with the learned projection networkADMM solver · Compressive sensing at m/d 0.1 and 0.03reconstruction qualityImproved
replace the wavelet l1 prior with the learned projection networkADMM solver · Blockwise inpainting on MS-Celeb-1Mreconstruction qualityImproved
use the single projection network instead of a specially-trained network when the measurement matrix is partially resampledcompressive sensing · Resampled Gaussian matrix A on MS-Celeb-1Mreconstruction qualityImproved
use the single projection network instead of a specially-trained network under measurement noisecompressive sensing · Gaussian noise on measurementsreconstruction qualityImproved
use the single projection network versus BM3D for denoisingImageNet-trained projector · Image denoising with phone-camera test imagesdenoising quality: outperforms BM3D when sigma is larger than 40Mixed
add the projection cost term (v - P(v)) rather than only reconstruction loss (ablation)projection network training · ADMM iterationsADMM stabilityImproved
add spatially varying noise and smoothing perturbations instead of plain Gaussian noise (ablation)projection network training · ADMM inputsgeneralization of projectorImproved
increase rho (ablation)ADMM with projector · Blockwise inpainting on ImageNetconvergence and output qualityMixed
add the latent-space classifier D_l (ablation)projection network training · projector trainingtraining stability and overfittingImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy